{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:17:15Z","timestamp":1780672635598,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747887","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"8517-8521","source":"Crossref","is-referenced-by-count":25,"title":["Improving CTC-Based Speech Recognition Via Knowledge Transferring from Pre-Trained Language Models"],"prefix":"10.1109","author":[{"given":"Keqi","family":"Deng","sequence":"first","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songjun","family":"Cao","sequence":"additional","affiliation":[{"name":"Tencent Cloud Xiaowei,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yike","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent Cloud Xiaowei,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Long","family":"Ma","sequence":"additional","affiliation":[{"name":"Tencent Cloud Xiaowei,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaofeng","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1048"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1955"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2404"},{"key":"ref11","first-page":"1403","article-title":"Imputer: Sequence modelling via imputation and dynamic programming","volume":"119","author":"chan","year":"2020","journal-title":"Proc ICML"},{"key":"ref12","first-page":"4171","article-title":"BERT: pretraining of deep bidirectional transformers for language understanding","volume":"1","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref13","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953075"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICSDA.2017.8384449"},{"key":"ref16","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume":"119","author":"chen","year":"2020","journal-title":"ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-srw.16"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3082299"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138707"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref4","article-title":"Non-autoregressive transformer-based end-to-end ASR using BERT","author":"yu","year":"2021","journal-title":"CoRR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3071668"},{"key":"ref6","article-title":"vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"ICLRE"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462576"},{"key":"ref7","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414594"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1186"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682586"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1179"},{"key":"ref22","article-title":"Adapt-and-adjust: Overcoming the long-tail problem of multilingual speech recognition","author":"winata","year":"2020","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053324"},{"key":"ref24","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054250"},{"key":"ref26","article-title":"AISHELL-2: transforming mandarin ASR research into industrial scale","author":"du","year":"2018","journal-title":"CoRR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688009"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747887.pdf?arnumber=9747887","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:11:08Z","timestamp":1661199068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747887\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747887","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}